I’m taking a different approach in today’s blog to discuss a problem I continue to run into when I am working with clients. And that is testing whether the response rates in a direct mail test are meaningful.
Now response rates are relatively uncomplicated to test. Anyone can do it. That’s because there are only two possible outcomes: Response or nonresponse.
After you click on the link, you will need to enter your data. The “base sizes” are the number of pieces mailed in each of your tests. The “proportions” are the number of responses for each test divided by the number of mailed. You can choose your confidence level (we recommend 90%), and then click calculate.
I suggest using a 90% confidence level because it is a high standard. That means if you have this difference in 100 tests, in 90 of those tests the difference will be real. The “Results” box will state either “Significant” or “NOT Significant.” You don’t need to understand statistics to use this tool!
Another helpful metric to know is your average gift size. Now, testing average gift size is more work to calculate, because the values you are testing can range from $0.01 to $1 million or more. That means you can’t use summary statistics (averages) to calculate significance. Instead, you need the entire gift distribution. Plus, you will need a more robust software tool than Excel to do this. We use SPSS.
We suggest that you talk with your analytics people to have them help you through testing average gift size differences.
Thank you for joining me for today’s stats class.